Breast Ultrasound Tumor Generation via Mask Generator and Text-Guided Network:A Clinically Controllable Framework with Downstream Evaluation

• URL: http://arxiv.org/abs/2507.07721v1
• Date: Thu, 10 Jul 2025 12:56:24 GMT
• Title: Breast Ultrasound Tumor Generation via Mask Generator and Text-Guided Network:A Clinically Controllable Framework with Downstream Evaluation
• Authors: Haoyu Pan, Hongxin Lin, Zetian Feng, Chuxuan Lin, Junyang Mo, Chu Zhang, Zijian Wu, Yi Wang, Qingqing Zheng,
• Abstract summary: We propose a clinically controllable generative framework for synthesizing breast ultrasound (BUS) images.<n>This framework integrates clinical descriptions with structural masks to generate tumors, enabling fine-grained control over tumor characteristics such as morphology, echogencity, and shape.<n>During inference, synthetic tumor masks serve as input to the generative framework, producing highly personalized synthetic BUS images with tumors that reflect real-world morphological diversity.
• Score: 6.147743049513793
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The development of robust deep learning models for breast ultrasound (BUS) image analysis is significantly constrained by the scarcity of expert-annotated data. To address this limitation, we propose a clinically controllable generative framework for synthesizing BUS images. This framework integrates clinical descriptions with structural masks to generate tumors, enabling fine-grained control over tumor characteristics such as morphology, echogencity, and shape. Furthermore, we design a semantic-curvature mask generator, which synthesizes structurally diverse tumor masks guided by clinical priors. During inference, synthetic tumor masks serve as input to the generative framework, producing highly personalized synthetic BUS images with tumors that reflect real-world morphological diversity. Quantitative evaluations on six public BUS datasets demonstrate the significant clinical utility of our synthetic images, showing their effectiveness in enhancing downstream breast cancer diagnosis tasks. Furthermore, visual Turing tests conducted by experienced sonographers confirm the realism of the generated images, indicating the framework's potential to support broader clinical applications.

Related papers

• Interactive Tumor Progression Modeling via Sketch-Based Image Editing [54.47725383502915]
  We propose SkEditTumor, a sketch-based diffusion model for controllable tumor progression editing.<n>By leveraging sketches as structural priors, our method enables precise modifications of tumor regions while maintaining structural integrity and visual realism.<n>Our contributions include a novel integration of sketches with diffusion models for medical image editing, fine-grained control over tumor progression visualization, and extensive validation across multiple datasets, setting a new benchmark in the field.
  arXiv  Detail & Related papers  (2025-03-10T00:04:19Z)
• CSG: A Context-Semantic Guided Diffusion Approach in De Novo Musculoskeletal Ultrasound Image Generation [1.727597257312416]
  We introduce a scalable semantic and context-conditioned generative model, coined CSG (Context-Semantic Guidance).<n>We demonstrate the ability of CSG to generate findings (pathological anomalies) in musculoskeletal (MSK) ultrasound images.<n>Results show that the synthetic images generated by CSG improve the performance of semantic segmentation models, exhibit enhanced similarity to real images, and are undistinguishable from real images according to a Turing test.
  arXiv  Detail & Related papers  (2024-12-08T06:48:09Z)
• Deep Generative Models Unveil Patterns in Medical Images Through Vision-Language Conditioning [3.4299097748670255]
  Deep generative models have significantly advanced medical imaging analysis by enhancing dataset size and quality. We employ a generative structure with hybrid conditions, combining clinical data and segmentation masks to guide the image synthesis process. Our approach differs from and presents a more challenging task than traditional medical report-guided synthesis due to the less visual correlation of our clinical information with the images.
  arXiv  Detail & Related papers  (2024-10-17T17:48:36Z)
• Mask-Enhanced Segment Anything Model for Tumor Lesion Semantic Segmentation [48.107348956719775]
  We introduce Mask-Enhanced SAM (M-SAM), an innovative architecture tailored for 3D tumor lesion segmentation. We propose a novel Mask-Enhanced Adapter (MEA) within M-SAM that enriches the semantic information of medical images with positional data from coarse segmentation masks. Our M-SAM achieves high segmentation accuracy and also exhibits robust generalization.
  arXiv  Detail & Related papers  (2024-03-09T13:37:02Z)
• Towards Generalizable Tumor Synthesis [48.45704270448412]
  Tumor synthesis enables the creation of artificial tumors in medical images, facilitating the training of AI models for tumor detection and segmentation. This paper made a progressive stride toward generalizable tumor synthesis by leveraging a critical observation. We have ascertained that generative AI models, e.g., Diffusion Models, can create realistic tumors generalized to a range of organs even when trained on a limited number of tumor examples from only one organ.
  arXiv  Detail & Related papers  (2024-02-29T18:57:39Z)
• Comparative Analysis of Segment Anything Model and U-Net for Breast Tumor Detection in Ultrasound and Mammography Images [0.15833270109954137]
  The technique employs two advanced deep learning architectures, namely U-Net and pretrained SAM, for tumor segmentation. The U-Net model is specifically designed for medical image segmentation. The pretrained SAM architecture incorporates a mechanism to capture spatial dependencies and generate segmentation results.
  arXiv  Detail & Related papers  (2023-06-21T18:49:21Z)
• Synthesis of Annotated Colorectal Cancer Tissue Images from Gland Layout [0.0]
  Synthetically generated images and annotations are valuable for training and evaluating algorithms in this domain. We propose an interactive framework generating pairs of realistic colorectal cancer histology images with corresponding glandular masks from glandular structure layouts.
  arXiv  Detail & Related papers  (2023-05-08T19:25:50Z)
• Image Synthesis with Disentangled Attributes for Chest X-Ray Nodule Augmentation and Detection [52.93342510469636]
  Lung nodule detection in chest X-ray (CXR) images is common to early screening of lung cancers. Deep-learning-based Computer-Assisted Diagnosis (CAD) systems can support radiologists for nodule screening in CXR. To alleviate the limited availability of such datasets, lung nodule synthesis methods are proposed for the sake of data augmentation.
  arXiv  Detail & Related papers  (2022-07-19T16:38:48Z)
• Deepfake histological images for enhancing digital pathology [0.40631409309544836]
  We develop a generative adversarial network model that synthesizes pathology images constrained by class labels. We investigate the ability of this framework in synthesizing realistic prostate and colon tissue images. We extend the approach to significantly more complex images from colon biopsies and show that the complex microenvironment in such tissues can also be reproduced.
  arXiv  Detail & Related papers  (2022-06-16T17:11:08Z)
• Texture Characterization of Histopathologic Images Using Ecological Diversity Measures and Discrete Wavelet Transform [82.53597363161228]
  This paper proposes a method for characterizing texture across histopathologic images with a considerable success rate. It is possible to quantify the intrinsic properties of such images with promising accuracy on two HI datasets.
  arXiv  Detail & Related papers  (2022-02-27T02:19:09Z)
• BI-RADS-Net: An Explainable Multitask Learning Approach for Cancer Diagnosis in Breast Ultrasound Images [69.41441138140895]
  This paper introduces BI-RADS-Net, a novel explainable deep learning approach for cancer detection in breast ultrasound images. The proposed approach incorporates tasks for explaining and classifying breast tumors, by learning feature representations relevant to clinical diagnosis. Explanations of the predictions (benign or malignant) are provided in terms of morphological features that are used by clinicians for diagnosis and reporting in medical practice.
  arXiv  Detail & Related papers  (2021-10-05T19:14:46Z)
• Learned super resolution ultrasound for improved breast lesion characterization [52.77024349608834]
  Super resolution ultrasound localization microscopy enables imaging of the microvasculature at the capillary level. In this work we use a deep neural network architecture that makes effective use of signal structure to address these challenges. By leveraging our trained network, the microvasculature structure is recovered in a short time, without prior PSF knowledge, and without requiring separability of the UCAs.
  arXiv  Detail & Related papers  (2021-07-12T09:04:20Z)
• Malignancy Prediction and Lesion Identification from Clinical Dermatological Images [65.1629311281062]
  We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images. We first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy.
  arXiv  Detail & Related papers  (2021-04-02T20:52:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.